5 papers
Rethinking Reverse KL as Adaptive Entropy Distillation
Shizhen Li, Zhiyu Shen, Yuyin Lu +4
Knowledge distillation (KD) is widely used to transfer the capabilities of large language models (LLMs) to smaller students, but existing objectives often struggle to balance faith…
Cross-Source Reasoning-based Correction for Author Name Disambiguation
Fanjin Zhang, Yunhe Pang, Bo Chen +4
Author name disambiguation is a critical challenge in academic search systems, often addressed through from-scratch and real-time disambiguation approaches. However, current algori…
MemBuilder: Reinforcing LLMs for Long-Term Memory Construction via Attributed Dense Rewards
Zhiyu Shen, Ziming Wu, Fuming Lai +2
Maintaining consistency in long-term dialogues remains a fundamental challenge for LLMs, as standard retrieval mechanisms often fail to capture the temporal evolution of historical…
HopWeaver: Cross-Document Synthesis of High-Quality and Authentic Multi-Hop Questions
Zhiyu Shen, Jiyuan Liu, Yunhe Pang +3
Multi-Hop Question Answering (MHQA) is crucial for evaluating the model's capability to integrate information from diverse sources. However, creating extensive and high-quality MHQ…
DesignQuizzer: A Community-Powered Conversational Agent for Learning Visual Design
Zhenhui Peng, Qiaoyi Chen, Zhiyu Shen +2
Online design communities, where members exchange free-form views on others' designs, offer a space for beginners to learn visual design. However, the content of these communities…